交易分析入门工具

• Outcome: Review
• Latest audit: Jul 26, 2026 · 6:03 PM UTC
• Version: 1.0.1

Overview

The skill is mainly a trading-analysis helper, but it asks for broad shell/write authority and external callback behavior that are not tightly scoped to that purpose.

Review this before installing. Use it only in a controlled workspace, avoid giving it callback URLs unless you trust the endpoint and expect analysis results to be sent there, and treat outputs as informational trading analysis rather than financial advice. The artifact does not show malicious code, but its requested authority is broader than its free analysis-only purpose needs.

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (6)

Intent-Code Divergence

Medium

• Confidence: 83% confidence
• Finding: The skill claims the free edition does not support automatic trading, yet it exposes broad exec/write tooling and explicitly mentions create/query/export operations. This creates a capability-to-documentation mismatch that could let the skill perform side effects beyond passive analysis, increasing the risk of unintended file modification, scripted actions, or downstream workflow abuse.

Context-Inappropriate Capability

Low

• Confidence: 76% confidence
• Finding: Callback URL support is not well justified for a single-instrument technical analysis skill and introduces an external data egress path. Even if intended for asynchronous completion, it could be abused to send analysis contents, prompts, or user-supplied data to attacker-controlled endpoints.

Context-Inappropriate Capability

Medium

• Confidence: 90% confidence
• Finding: The manifest declares generic exec and write capabilities even though the documented purpose is analysis-oriented. Overbroad capabilities violate least privilege and increase the chance that prompt-triggered behavior can execute local code or modify files in ways users would not expect from a trading-analysis helper.

Vague Triggers

High

• Confidence: 87% confidence
• Finding: The description includes broad trigger terms such as data analysis, automation, machine learning, natural language, and finance, which greatly exceed the stated Vegas Channel trading purpose. This can cause the skill to activate in unrelated contexts, where its exec/write capabilities and ambiguous behavior increase the risk of misuse or accidental invocation.

Vague Triggers

High

• Confidence: 91% confidence
• Finding: The capability coverage statement defines an extremely broad activation scope and claims support for many loosely related scenarios without clear limits. In combination with powerful tools, this broad self-routing language can make the skill engage in contexts where its behavior is unsafe, misleading, or outside user intent.

Missing User Warnings

Medium

• Confidence: 80% confidence
• Finding: The markdown introduces callback URL behavior without any warning about privacy, integrity, or outbound network risks. Users may not realize that providing a URL can transmit request-derived data externally, creating opportunities for data leakage, SSRF-like misuse, or delivery to untrusted endpoints.

VirusTotal

VirusTotal findings are pending for this skill version.

Static analysis

No suspicious patterns detected.